blob: f5cc14b33808885e852282f98a27398b9ccdfba0 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
#!/bin/sh
#See http://www.unicode.org/reports/tr44/
#
#Me Enclosing_Mark an enclosing combining mark
#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width)
#Cf Format a format control character
#
UNICODEWIDTH_H=../unicode_width.h
if ! test -d unicode; then
mkdir unicode
fi &&
( cd unicode &&
if ! test -f UnicodeData.txt; then
wget http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
fi &&
if ! test -f EastAsianWidth.txt; then
wget http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt
fi &&
if ! test -d uniset; then
git clone https://github.com/depp/uniset.git
fi &&
(
cd uniset &&
if ! test -x uniset; then
autoreconf -i &&
./configure --enable-warnings=-Werror CFLAGS='-O0 -ggdb'
fi &&
make
) && {
UNICODE_DIR=. && export UNICODE_DIR &&
echo "static const struct interval zero_width[] = {" &&
uniset/uniset --32 cat:Me,Mn,Cf + U+1160..U+11FF - U+00AD |
grep -v plane &&
echo "};" &&
echo "static const struct interval double_width[] = {" &&
uniset/uniset --32 eaw:F,W &&
echo "};"
} >$UNICODEWIDTH_H
)
|
